1.Exercises in R for Data Science 3.5.1(2,3)

#3.5.1(2)What do the empty cells in plot with facet_grid(drv ~ cyl) mean? How do they relate to this plot?
library(ggplot2)
ggplot(data = mpg) + 
  geom_point(mapping = aes(x = drv, y = cyl))

ggplot(data = mpg) + 
  geom_point(mapping = aes(x = drv, y = cyl))+facet_grid(drv ~ cyl)

# The empty cells in facet_grid(drv~cyl) mean that there are no combination of two variables in those rows and columns.


#3.5.1(3)What plots does the following code make? What does . do?
ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy)) +
  facet_grid(drv ~ .)

ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy)) +
  facet_grid(. ~ cyl)

# If we do not want to facet in the rows or columns dimension, use a . instead of a variable name
  1. Exercises in R for Data Science 3.6.1(6),
#3.6.1(6)Recreate the R code necessary to generate the following graphs
library(ggplot2)

graph1<-ggplot(data=mpg)+geom_point(mapping = aes(x = displ, y = hwy,size=class))+geom_smooth(mapping = aes(x = displ, y = hwy,se = FALSE))
## Warning: Ignoring unknown aesthetics: se
graph2<-ggplot(data=mpg)+geom_point(mapping = aes(x = displ, y = hwy,size=class))+geom_smooth(mapping = aes(x = displ, y = hwy,group=drv,se = FALSE))
## Warning: Ignoring unknown aesthetics: se
graph3<-ggplot(data=mpg)+geom_point(mapping = aes(x = displ, y = hwy,color=drv,size=class))+geom_smooth(mapping = aes(x = displ, y = hwy,color=drv,se = FALSE))
## Warning: Ignoring unknown aesthetics: se
graph4<-ggplot(data=mpg)+geom_point(mapping = aes(x = displ, y = hwy,color=drv,size=class))+geom_smooth(mapping = aes(x = displ, y = hwy,se = FALSE))
## Warning: Ignoring unknown aesthetics: se
graph5<-ggplot(data=mpg)+geom_point(mapping = aes(x = displ, y = hwy,color=drv,size=class))+geom_smooth(mapping = aes(x = displ, y = hwy,linetype=drv,se = FALSE))
## Warning: Ignoring unknown aesthetics: se
graph6<-ggplot(data=mpg)+geom_point(mapping = aes(x = displ, y = hwy,color=drv,size=class))
par(mfrow=c(3,2))
graph1
## Warning: Using size for a discrete variable is not advised.
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

graph2
## Warning: Using size for a discrete variable is not advised.
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

graph3
## Warning: Using size for a discrete variable is not advised.
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

graph4
## Warning: Using size for a discrete variable is not advised.
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

graph5
## Warning: Using size for a discrete variable is not advised.
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

graph6
## Warning: Using size for a discrete variable is not advised.

3.Exercises in R for Data Science 5.2.4(1,2,3,4)

#5.2.4(1)
#1.Had an arrival delay of two or more hours
library(nycflights13)
library(tidyverse)
## ─ Attaching packages ────────────────────────────── tidyverse 1.2.1 ─
## ✔ tibble  1.4.2     ✔ purrr   0.2.5
## ✔ tidyr   0.8.1     ✔ dplyr   0.7.6
## ✔ readr   1.1.1     ✔ stringr 1.3.1
## ✔ tibble  1.4.2     ✔ forcats 0.3.0
## ─ Conflicts ─────────────────────────────── tidyverse_conflicts() ─
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
filter(flights, arr_delay >= 120)
#2.Flew to Houston (IAH or HOU)
filter(flights,dest %in% c("IAH", "HOU"))
#3.Were operated by United, American, or Delta
filter(flights, carrier %in% c("AA", "DL", "UA"))
#4.Departed in summer (July, August, and September)
filter(flights, month %in% c(7:9))
#5.Arrived more than two hours late, but didn’t leave late
filter(flights, arr_delay > 120&dep_delay <= 0)
#6.Were delayed by at least an hour, but made up over 30 minutes in flight
filter(flights, dep_delay >= 60&(dep_delay - arr_delay > 30))
#7.Departed between midnight and 6am (inclusive)
filter(flights, dep_time >= 0 & dep_time <= 600)
#5.2.4(2)Another useful dplyr filtering helper is between(). What does it do? Can you use it to simplify the code needed to answer the previous challenges?
# between is used to express the interval in the &(and) situation.
filter(flights, between(dep_time, 0, 600))
#5.2.4(3)How many flights have a missing dep_time? What other variables are missing? What might these rows represent?
sum(is.na(flights$dep_time))
## [1] 8255
sum(is.na(flights$sched_dep_time))
## [1] 0
sum(is.na(flights$dep_delay))
## [1] 8255
sum(is.na(flights$arr_time))
## [1] 8713
sum(is.na(flights$sched_arr_time))
## [1] 0
sum(is.na(flights$arr_delay))
## [1] 9430
sum(is.na(flights$carrier))
## [1] 0
map_dbl(flights, ~ sum(is.na(.x)))
##           year          month            day       dep_time sched_dep_time 
##              0              0              0           8255              0 
##      dep_delay       arr_time sched_arr_time      arr_delay        carrier 
##           8255           8713              0           9430              0 
##         flight        tailnum         origin           dest       air_time 
##              0           2512              0              0           9430 
##       distance           hour         minute      time_hour 
##              0              0              0              0
#5.2.4(4)Why is NA ^ 0 not missing? Why is NA | TRUE not missing? Why is FALSE & NA not missing? Can you figure out the general rule? (NA * 0 is a tricky counterexample!)

## Every NA^0=1.NA|TRUE always equals to TRUE by the definition of or. FALSE & NA can always be tested TRUE or FALSE.